Applied AI Engineer, Codex Core Agent
San Francisco • FullTime
Posted 5mo ago
Remote Work Policy
On-site
Employment Type
FullTime
Categories
AI Agent Engineer
About the job
We are seeking applied AI engineers to transform Codex agents from impressive demonstrations into dependable tools. This role focuses on enhancing agent performance for real-world software engineering tasks, bridging the gap between research capabilities and practical usefulness. You will collaborate closely with research, infrastructure, and product teams to ensure agents are powerful, steerable, and reliable. The objective is to achieve measurable improvements in solve rates, usefulness, and economic value for users by refining model behavior and system integration.
Responsibilities
- Design and iterate on agent behaviors for real-world coding tasks and long-horizon workflows.
- Collaborate with research to develop and run evaluations measuring agent performance, regressions, failure modes, and edge cases.
- Improve performance through prompting, tool-use strategies, context construction, and model-facing experimentation.
- Analyze production failures and systematically enhance robustness and reliability.
- Build feedback loops and data systems to feed better real-task data into evaluation and research.
- Partner with product teams to shape user-facing agent experiences and their dependencies.
- Define standards for agent performance on complex end-to-end tasks.
Requirements
- Experience building or shipping machine learning or LLM-powered products.
- Proficiency in Python and modern ML tooling.
- Experience with model evaluation, fine-tuning, or prompt design.
- Systems thinking approach focused on user outcomes.
- Enjoy debugging real-world failures and implementing improvements.
- Desire to work on the layer that translates research potential into functional user systems.